def by_labels(X, y):
"""Split up X into a list if Xs, one for each unique entry in y.
Parameters
----------
X : a 2d array-like (n_features x n_sample)
The feature matrix
y : a 1d array-like
The labels for X
Return
------
Xs : seq-like, containing 2D arrays (n_feature x n_sample)
The split up Xs
ys : seq-like, containing 1D arrays
The y matching each X in Xs
"""
# ----`
# Find all samples
y_masks = []
unique_y = sorted(np.unique(y))
unique_y = unique_sorted_with_nan(unique_y)
for y_i in unique_y:
y_masks.append(np.str(y_i) == y)
# And split each feature into seperate Xs
Xs = []
ys = []
for mask in y_masks:
Xs.append(X[mask,])
ys.append(y[mask])
return Xs, ys
def __init__(self, y, indices=True):
self.y = np.array(y)
self.uniquey = sorted(list(set(self.y.tolist())))
self.uniquey = unique_sorted_with_nan(self.unique_y)
self.n = len(self.uniquey)
self.indices = indices
def by_labels(X, y):
"""Split up X into a list if Xs, one for each unique entry in y.
Parameters
----------
X : a 2d array-like (n_features x n_sample)
The feature matrix
y : a 1d array-like
The labels for X
Return
------
Xs : seq-like, containing 2D arrays (n_feature x n_sample)
The split up Xs
ys : seq-like, containing 1D arrays
The y matching each X in Xs
"""
# ----`
# Find all samples
y_masks = []
unique_y = sorted(np.unique(y))
unique_y = unique_sorted_with_nan(unique_y)
for y_i in unique_y:
y_masks.append(np.str(y_i) == y)
# And split each feature into seperate Xs
Xs = []
ys = []
for mask in y_masks:
Xs.append(X[mask, ])
ys.append(y[mask])
return Xs, ys
def __init__(self, y, indices=True):
self.y = np.array(y)
self.uniquey = sorted(list(set(self.y.tolist())))
self.uniquey = unique_sorted_with_nan(self.unique_y)
self.n = len(self.uniquey)
self.indices = indices
def eva(X, y, trial_index, window, tr):
"""Average trials for each feature in X
Parameters
----------
X : 2D array-like (n_sample, n_feature)
The data to decompose
y : 1D array, None by default
Sample labels for the data. In y, np.nan and 'nan' values
are ignored.
trial_index : 1D array (n_sample, )
Each unique entry should match a trial.
window : int
Trial length
Return
------
Xeva : a 2D arrays (n_feature*unique_y, window)
The average trials
feature_names : 1D array
The names of the features (taken from y)
"""
evas = []
eva_names = []
scaler = MinMaxScaler(feature_range=(0, 1))
for j in range(X.shape[1]):
Xtrials = []
xj = X[:,j][:,np.newaxis] ## Need 2D
# Each feature into trials, rescale too
Xtrial, feature_names = by_trial(xj, trial_index, window, y)
Xtrial = scaler.fit_transform(Xtrial.astype(np.float))
unique_fn = sorted(np.unique(feature_names))
unique_fn = unique_sorted_with_nan(unique_fn)
# and again by unique_y/fe]ature_names
Xlabels, _ = by_labels(X=Xtrial.transpose(), y=feature_names)
# put all that togthether
Xtrials.extend([Xl.transpose() for Xl in Xlabels])
# and average the trials then
# name names.
evas.extend([Xt.mean(axis=1) for Xt in Xtrials])
eva_names.extend(unique_fn)
# Reshape : (window, len(unique_y)*n_features)
Xeva = np.vstack(evas).transpose()
eva_names = np.asarray(eva_names)
assert checkX(Xeva)
assert Xeva.shape[0] == window, ("After EVA rows not equal to window")
assert Xeva.shape[1] == len(unique_fn) * X.shape[1], ("After"
"EVA wrong number of features")
assert eva_names.shape[0] == Xeva.shape[1], ("eva_names and Xeva"
"don't match")
return Xeva, eva_names
def eva(X, y, trial_index, window, tr):
"""Average trials for each feature in X
Parameters
----------
X : 2D array-like (n_sample, n_feature)
The data to decompose
y : 1D array, None by default
Sample labels for the data. In y, np.nan and 'nan' values
are ignored.
trial_index : 1D array (n_sample, )
Each unique entry should match a trial.
window : int
Trial length
Return
------
Xeva : a 2D arrays (n_feature*unique_y, window)
The average trials
feature_names : 1D array
The names of the features (taken from y)
"""
evas = []
eva_names = []
scaler = MinMaxScaler(feature_range=(0, 1))
for j in range(X.shape[1]):
Xtrials = []
xj = X[:, j][:, np.newaxis] ## Need 2D
# Each feature into trials, rescale too
Xtrial, feature_names = by_trial(xj, trial_index, window, y)
Xtrial = scaler.fit_transform(Xtrial.astype(np.float))
unique_fn = sorted(np.unique(feature_names))
unique_fn = unique_sorted_with_nan(unique_fn)
# and again by unique_y/fe]ature_names
Xlabels, _ = by_labels(X=Xtrial.transpose(), y=feature_names)
# put all that togthether
Xtrials.extend([Xl.transpose() for Xl in Xlabels])
# and average the trials then
# name names.
evas.extend([Xt.mean(axis=1) for Xt in Xtrials])
eva_names.extend(unique_fn)
# Reshape : (window, len(unique_y)*n_features)
Xeva = np.vstack(evas).transpose()
eva_names = np.asarray(eva_names)
assert checkX(Xeva)
assert Xeva.shape[0] == window, ("After EVA rows not equal to window")
assert Xeva.shape[1] == len(unique_fn) * X.shape[1], (
"After"
"EVA wrong number of features")
assert eva_names.shape[0] == Xeva.shape[1], ("eva_names and Xeva"
"don't match")
return Xeva, eva_names
def fir(X, y, trial_index, window, tr):
""" Average trials for each feature in X, using Burock's
(2000) method.
Parameters
----------
X : 2D array-like (n_sample, n_feature)
The data to decompose
y : 1D array, None by default
Sample labels for the data. In y, np.nan and 'nan' values
are treated as baseline labels.
trial_index : 1D array (n_sample, )
Each unique entry should match a trial.
window : int
Trial length
Return
------
Xfir : a 2D arrays (n_feature*unique_y, window)
The average trials
feature_names : 1D array
"""
# Norm then pad.
scaler = MinMaxScaler(feature_range=(0, 1))
X = scaler.fit_transform(X.astype(np.float))
X = np.vstack([X, np.ones((window, X.shape[1]), dtype=np.float)])
# Save the org y names
ynames = sorted(np.unique(y))
ynames = unique_sorted_with_nan(ynames)
# y becomes integers
y = create_y(y)
# Make the design matrix.
dm = _create_dm(y, window)
# dm DEBUG
#import time
#np.savetxt("dm-{0}".format(time.strftime("%m_%d_%Y_%H_%s_%m")), dm, fmt="%1.0f")
dm = np.matrix(dm)
# FIR!
fir_names = []
firs = []
for j in range(X.shape[1]):
x = np.matrix(X[:, j])
fir = np.array(np.linalg.pinv(dm.T * dm) * dm.T * x.T)[0:-1]
## Drop dummy
fir = fir.reshape(len(ynames) - 1, window)
firs.append(fir)
fir_names.extend(ynames[1:]) ## Drop nan/baseline
Xfir = np.vstack(firs).transpose()
fir_names = np.asarray(fir_names)
assert checkX(Xfir)
assert Xfir.shape[0] == window, ("After FIR rows not equal to window")
assert Xfir.shape[1] == (len(ynames[1:]) *
X.shape[1]), ("After"
"FIR wrong number of features")
assert fir_names.shape[0] == Xfir.shape[1], ("fir_names and Xfir"
"don't match")
return Xfir, fir_names
def fir(X, y, trial_index, window, tr):
""" Average trials for each feature in X, using Burock's
(2000) method.
Parameters
----------
X : 2D array-like (n_sample, n_feature)
The data to decompose
y : 1D array, None by default
Sample labels for the data. In y, np.nan and 'nan' values
are treated as baseline labels.
trial_index : 1D array (n_sample, )
Each unique entry should match a trial.
window : int
Trial length
Return
------
Xfir : a 2D arrays (n_feature*unique_y, window)
The average trials
feature_names : 1D array
"""
# Norm then pad.
scaler = MinMaxScaler(feature_range=(0, 1))
X = scaler.fit_transform(X.astype(np.float))
X = np.vstack([X, np.ones((window, X.shape[1]), dtype=np.float)])
# Save the org y names
ynames = sorted(np.unique(y))
ynames = unique_sorted_with_nan(ynames)
# y becomes integers
y = create_y(y)
# Make the design matrix.
dm = _create_dm(y, window)
# dm DEBUG
#import time
#np.savetxt("dm-{0}".format(time.strftime("%m_%d_%Y_%H_%s_%m")), dm, fmt="%1.0f")
dm = np.matrix(dm)
# FIR!
fir_names = []
firs = []
for j in range(X.shape[1]):
x = np.matrix(X[:,j])
fir = np.array(np.linalg.pinv(dm.T * dm) * dm.T * x.T)[0:-1]
## Drop dummy
fir = fir.reshape(len(ynames)-1, window)
firs.append(fir)
fir_names.extend(ynames[1:]) ## Drop nan/baseline
Xfir = np.vstack(firs).transpose()
fir_names = np.asarray(fir_names)
assert checkX(Xfir)
assert Xfir.shape[0] == window, ("After FIR rows not equal to window")
assert Xfir.shape[1] == (len(ynames[1:]) * X.shape[1]), ("After"
"FIR wrong number of features")
assert fir_names.shape[0] == Xfir.shape[1], ("fir_names and Xfir"
"don't match")
return Xfir, fir_names
